{"url":"/sota/thermal-image-segmentation-on-mfn-dataset","task":{"name":"Thermal Image Segmentation","url":"/task/thermal-image-segmentation","note":null},"dataset":{"name":"MFN Dataset","url":"/dataset/mfnet"},"category":"Computer Vision","categories":["Computer Vision","Methodology"],"category_note":null,"description":null,"description_from":null,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["mIOU","Frame (fps)"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"mIOU":null,"Frame (fps)":null}},"counts":{"rows":55,"rows_with_code":45,"rows_with_paper_page":55,"rows_dated":55,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"RoadFormer+ (ConvNeXt-L)","metrics":{"mIOU":"62.7"},"uses_additional_data":false,"paper_date":"2024-07-31","paper":"/paper/roadformer-delivering-rgb-x-scene-parsing","paper_url":"https://arxiv.org/abs/2407.21631v2","paper_title":"RoadFormer+: Delivering RGB-X Scene Parsing through Scale-Aware Information Decoupling and Advanced Heterogeneous Feature Fusion","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":2,"model":"HAPNet","metrics":{"mIOU":"61.5"},"uses_additional_data":false,"paper_date":"2024-04-04","paper":"/paper/hapnet-toward-superior-rgb-thermal-scene","paper_url":"https://arxiv.org/abs/2404.03527v2","paper_title":"HAPNet: Toward Superior RGB-Thermal Scene Parsing via Hybrid, Asymmetric, and Progressive Heterogeneous Feature Fusion","code":"https://github.com/LiJiahang617/HAPNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"CRM_RGBT_Seg","metrics":{"mIOU":"61.4"},"uses_additional_data":false,"paper_date":"2023-03-30","paper":"/paper/complementary-random-masking-for-rgb-thermal","paper_url":"https://arxiv.org/abs/2303.17386v2","paper_title":"Complementary Random Masking for RGB-Thermal Semantic Segmentation","code":"https://github.com/UkcheolShin/CRM_RGBTSeg","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":5,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":4,"model":"Sigma-base","metrics":{"mIOU":"61.3"},"uses_additional_data":false,"paper_date":"2024-04-05","paper":"/paper/sigma-siamese-mamba-network-for-multi-modal","paper_url":"https://arxiv.org/abs/2404.04256v2","paper_title":"Sigma: Siamese Mamba Network for Multi-Modal Semantic Segmentation","code":"https://github.com/zifuwan/sigma","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"CSFNet-2","metrics":{"Frame (fps)":"72.7 (3090)","mIOU":"59.98"},"uses_additional_data":false,"paper_date":"2024-07-01","paper":"/paper/csfnet-a-cosine-similarity-fusion-network-for","paper_url":"https://arxiv.org/abs/2407.01328v1","paper_title":"CSFNet: A Cosine Similarity Fusion Network for Real-Time RGB-X Semantic Segmentation of Driving Scenes","code":"https://github.com/Danial-Qashqai/CSFNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"CMNeXt (B4)","metrics":{"mIOU":"59.9"},"uses_additional_data":false,"paper_date":"2023-03-02","paper":"/paper/delivering-arbitrary-modal-semantic","paper_url":"https://arxiv.org/abs/2303.01480v1","paper_title":"Delivering Arbitrary-Modal Semantic Segmentation","code":"https://github.com/jamycheung/DELIVER","n_code_links":1,"syntology":{"n_ran":7,"n_unverified":0,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":7,"model":"CMX (B4)","metrics":{"mIOU":"59.7"},"uses_additional_data":false,"paper_date":"2022-03-09","paper":"/paper/cmx-cross-modal-fusion-for-rgb-x-semantic","paper_url":"https://arxiv.org/abs/2203.04838v5","paper_title":"CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers","code":"https://github.com/huaaaliu/rgbx_semantic_segmentation","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":8,"model":"DPLNet","metrics":{"mIOU":"59.3"},"uses_additional_data":false,"paper_date":"2023-12-01","paper":"/paper/efficient-multimodal-semantic-segmentation","paper_url":"https://arxiv.org/abs/2312.00360v2","paper_title":"Efficient Multimodal Semantic Segmentation via Dual-Prompt Learning","code":"https://github.com/shaohuadong2021/dplnet","n_code_links":1,"syntology":null},{"rank_in_archive_order":9,"model":"UniRGB-IR","metrics":{"mIOU":"59.3"},"uses_additional_data":false,"paper_date":"2024-04-26","paper":"/paper/unirgb-ir-a-unified-framework-for-visible","paper_url":"https://arxiv.org/abs/2404.17360v2","paper_title":"UniRGB-IR: A Unified Framework for RGB-Infrared Semantic Tasks via Adapter Tuning","code":"https://github.com/potsui99/unirgb-ir","n_code_links":1,"syntology":null},{"rank_in_archive_order":10,"model":"SHIFNet","metrics":{"mIOU":"59.2"},"uses_additional_data":false,"paper_date":"2025-03-04","paper":"/paper/unveiling-the-potential-of-segment-anything","paper_url":"https://arxiv.org/abs/2503.02581v1","paper_title":"Unveiling the Potential of Segment Anything Model 2 for RGB-Thermal Semantic Segmentation with Language Guidance","code":"https://github.com/iasakit3t/shifnet","n_code_links":1,"syntology":null},{"rank_in_archive_order":11,"model":"IGFNet(B2)","metrics":{"mIOU":"59.0"},"uses_additional_data":false,"paper_date":"2023-12-04","paper":"/paper/igfnet-illumination-guided-fusion-network-for","paper_url":"https://ieeexplore.ieee.org/abstract/document/10354613","paper_title":"IGFNet: Illumination-Guided Fusion Network for Semantic Scene Understanding using RGB-Thermal Images","code":"https://github.com/lab-sun/IGFNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":12,"model":"EAEFNet (ResNet-152)","metrics":{"mIOU":"58.9"},"uses_additional_data":false,"paper_date":"2023-03-28","paper":"/paper/explicit-attention-enhanced-fusion-for-rgb","paper_url":"https://arxiv.org/abs/2303.15710v1","paper_title":"Explicit Attention-Enhanced Fusion for RGB-Thermal Perception Tasks","code":"https://github.com/freeformrobotics/eaefnet","n_code_links":1,"syntology":null},{"rank_in_archive_order":13,"model":"CAINet (MobileNet-V2)","metrics":{"mIOU":"58.6%"},"uses_additional_data":false,"paper_date":"2024-01-03","paper":"/paper/context-aware-interaction-network-for-rgb-t","paper_url":"https://arxiv.org/abs/2401.01624v1","paper_title":"Context-Aware Interaction Network for RGB-T Semantic Segmentation","code":"https://github.com/yinglv1106/cainet","n_code_links":1,"syntology":null},{"rank_in_archive_order":14,"model":"SpiderMesh (B4)","metrics":{"mIOU":"58.4"},"uses_additional_data":false,"paper_date":"2023-03-15","paper":"/paper/spidermesh-spatial-aware-demand-guided","paper_url":"https://arxiv.org/abs/2303.08692v2","paper_title":"SpiderMesh: Spatial-aware Demand-guided Recursive Meshing for RGB-T Semantic Segmentation","code":"https://github.com/leofansq/spidermesh","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":15,"model":"CMX (B2)","metrics":{"mIOU":"58.2"},"uses_additional_data":false,"paper_date":"2022-03-09","paper":"/paper/cmx-cross-modal-fusion-for-rgb-x-semantic","paper_url":"https://arxiv.org/abs/2203.04838v5","paper_title":"CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers","code":"https://github.com/huaaaliu/rgbx_semantic_segmentation","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":16,"model":"StitchFusion","metrics":{"mIOU":"58.13"},"uses_additional_data":false,"paper_date":"2024-08-02","paper":"/paper/2408-01343","paper_url":"https://arxiv.org/abs/2408.01343v1","paper_title":"StitchFusion: Weaving Any Visual Modalities to Enhance Multimodal Semantic Segmentation","code":"https://github.com/libingyu01/stitchfusion-stitchfusion-weaving-any-visual-modalities-to-enhance-multimodal-semantic-segmentation","n_code_links":1,"syntology":null},{"rank_in_archive_order":17,"model":"SpiderMesh (ResNet-152)","metrics":{"mIOU":"57.9"},"uses_additional_data":false,"paper_date":"2023-03-15","paper":"/paper/spidermesh-spatial-aware-demand-guided","paper_url":"https://arxiv.org/abs/2303.08692v2","paper_title":"SpiderMesh: Spatial-aware Demand-guided Recursive Meshing for RGB-T Semantic Segmentation","code":"https://github.com/leofansq/spidermesh","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":18,"model":"CACFNet","metrics":{"mIOU":"57.8"},"uses_additional_data":false,"paper_date":"2023-09-14","paper":"/paper/cacfnet-cross-modal-attention-cascaded-fusion","paper_url":"https://ieeexplore.ieee.org/abstract/document/10251592","paper_title":"CACFNet: Cross-Modal Attention Cascaded Fusion Network for RGB-T Urban Scene Parsing","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":19,"model":"VPFNet","metrics":{"mIOU":"57.61"},"uses_additional_data":false,"paper_date":"2023-07-17","paper":"/paper/variational-probabilistic-fusion-network-for","paper_url":"https://arxiv.org/abs/2307.08536v1","paper_title":"Variational Probabilistic Fusion Network for RGB-T Semantic Segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":20,"model":"EGFNet(ConvNeXt)","metrics":{"mIOU":"57.5"},"uses_additional_data":false,"paper_date":"2023-08-15","paper":"/paper/egfnet-edge-aware-guidance-fusion-network-for","paper_url":"https://ieeexplore.ieee.org/abstract/document/10234530","paper_title":"EGFNet: Edge-Aware Guidance Fusion Network for RGB–Thermal Urban Scene Parsing","code":"https://github.com/shaohuadong2021/egfnet","n_code_links":1,"syntology":null},{"rank_in_archive_order":21,"model":"DooDLeNet","metrics":{"mIOU":"57.3"},"uses_additional_data":false,"paper_date":"2022-04-21","paper":"/paper/doodlenet-double-deeplab-enhanced-feature","paper_url":"https://arxiv.org/abs/2204.10266v1","paper_title":"DooDLeNet: Double DeepLab Enhanced Feature Fusion for Thermal-color Semantic Segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":22,"model":"PAIF","metrics":{"mIOU":"56.5"},"uses_additional_data":false,"paper_date":"2023-08-08","paper":"/paper/paif-perception-aware-infrared-visible-image","paper_url":"https://arxiv.org/abs/2308.03979v1","paper_title":"PAIF: Perception-Aware Infrared-Visible Image Fusion for Attack-Tolerant Semantic Segmentation","code":"https://github.com/LiuZhu-CV/BDLFusion","n_code_links":3,"syntology":{"n_ran":23,"n_unverified":4,"n_samples":27,"n_pointer_only_licence":11}},{"rank_in_archive_order":23,"model":"RSFNet (ResNet-101)","metrics":{"mIOU":"56.2"},"uses_additional_data":false,"paper_date":"2023-06-17","paper":"/paper/residual-spatial-fusion-network-for-rgb","paper_url":"https://arxiv.org/abs/2306.10364v1","paper_title":"Residual Spatial Fusion Network for RGB-Thermal Semantic Segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":24,"model":"GEBNet","metrics":{"mIOU":"56.2"},"uses_additional_data":false,"paper_date":"2022-10-31","paper":"/paper/gebnet-graph-enhancement-branch-network-for","paper_url":"https://ieeexplore.ieee.org/abstract/document/9937048","paper_title":"GEBNet: Graph-Enhancement Branch Network for RGB-T Scene Parsing","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":25,"model":"SegMiF","metrics":{"mIOU":"56.1"},"uses_additional_data":false,"paper_date":"2023-08-04","paper":"/paper/multi-interactive-feature-learning-and-a-full","paper_url":"https://arxiv.org/abs/2308.02097v1","paper_title":"Multi-interactive Feature Learning and a Full-time Multi-modality Benchmark for Image Fusion and Segmentation","code":"https://github.com/jinyuanliu-cv/segmif","n_code_links":2,"syntology":{"n_ran":19,"n_unverified":7,"n_samples":26,"n_pointer_only_licence":13}},{"rank_in_archive_order":26,"model":"SpiderMesh (ResNet-101)","metrics":{"mIOU":"56.1"},"uses_additional_data":false,"paper_date":"2023-03-15","paper":"/paper/spidermesh-spatial-aware-demand-guided","paper_url":"https://arxiv.org/abs/2303.08692v2","paper_title":"SpiderMesh: Spatial-aware Demand-guided Recursive Meshing for RGB-T Semantic Segmentation","code":"https://github.com/leofansq/spidermesh","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":27,"model":"MTANet","metrics":{"mIOU":"56.1"},"uses_additional_data":false,"paper_date":"2022-04-05","paper":"/paper/mtanet-multitask-aware-network-with","paper_url":"https://ieeexplore.ieee.org/abstract/document/9749834","paper_title":"MTANet: Multitask-Aware Network With Hierarchical Multimodal Fusion for RGB-T Urban Scene Understanding","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":28,"model":"CENet","metrics":{"mIOU":"56.1"},"uses_additional_data":false,"paper_date":"2023-02-22","paper":"/paper/cekd-cross-modal-edge-privileged-knowledge","paper_url":"https://ieeexplore.ieee.org/document/10049523","paper_title":"CEKD: Cross-Modal Edge-Privileged Knowledge Distillation for Semantic Scene Understanding Using Only Thermal Images","code":"https://github.com/lab-sun/CEKD","n_code_links":1,"syntology":null},{"rank_in_archive_order":29,"model":"CSFNet-1","metrics":{"Frame (fps)":"106.3 (3090)","mIOU":"56.05"},"uses_additional_data":false,"paper_date":"2024-07-01","paper":"/paper/csfnet-a-cosine-similarity-fusion-network-for","paper_url":"https://arxiv.org/abs/2407.01328v1","paper_title":"CSFNet: A Cosine Similarity Fusion Network for Real-Time RGB-X Semantic Segmentation of Driving Scenes","code":"https://github.com/Danial-Qashqai/CSFNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":30,"model":"CSRPNet","metrics":{"mIOU":"56.0"},"uses_additional_data":false,"paper_date":"2023-08-24","paper":"/paper/channel-and-spatial-relation-propagation","paper_url":"https://arxiv.org/abs/2308.12534v1","paper_title":"Channel and Spatial Relation-Propagation Network for RGB-Thermal Semantic Segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":31,"model":"EAFFNet (ResNet-50)","metrics":{"mIOU":"55.9"},"uses_additional_data":false,"paper_date":"2023-03-28","paper":"/paper/explicit-attention-enhanced-fusion-for-rgb","paper_url":"https://arxiv.org/abs/2303.15710v1","paper_title":"Explicit Attention-Enhanced Fusion for RGB-Thermal Perception Tasks","code":"https://github.com/freeformrobotics/eaefnet","n_code_links":1,"syntology":null},{"rank_in_archive_order":32,"model":"FEANet","metrics":{"mIOU":"55.3"},"uses_additional_data":false,"paper_date":"2021-10-18","paper":"/paper/feanet-feature-enhanced-attention-network-for","paper_url":"https://arxiv.org/abs/2110.08988v1","paper_title":"FEANet: Feature-Enhanced Attention Network for RGB-Thermal Real-time Semantic Segmentation","code":"https://github.com/matrixgame2018/FEANet","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":1,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":33,"model":"LASNet","metrics":{"mIOU":"54.9"},"uses_additional_data":false,"paper_date":"2022-10-26","paper":"/paper/rgb-t-semantic-segmentation-with-location","paper_url":"https://arxiv.org/abs/2210.14530v1","paper_title":"RGB-T Semantic Segmentation with Location, Activation, and Sharpening","code":"https://github.com/mathlee/lasnet","n_code_links":1,"syntology":null},{"rank_in_archive_order":34,"model":"ABMDRNet","metrics":{"mIOU":"54.8"},"uses_additional_data":false,"paper_date":"2021-06-19","paper":"/paper/abmdrnet-adaptive-weighted-bi-directional","paper_url":"http://openaccess.thecvf.com//content/CVPR2021/html/Zhang_ABMDRNet_Adaptive-Weighted_Bi-Directional_Modality_Difference_Reduction_Network_for_RGB-T_Semantic_CVPR_2021_paper.html","paper_title":"ABMDRNet: Adaptive-Weighted Bi-Directional Modality Difference Reduction Network for RGB-T Semantic Segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":35,"model":"EGFNet","metrics":{"mIOU":"54.8"},"uses_additional_data":false,"paper_date":"2021-12-09","paper":"/paper/edge-aware-guidance-fusion-network-for-rgb","paper_url":"https://arxiv.org/abs/2112.05144v1","paper_title":"Edge-aware Guidance Fusion Network for RGB Thermal Scene Parsing","code":"https://github.com/shaohuadong2021/egfnet","n_code_links":1,"syntology":null},{"rank_in_archive_order":36,"model":"SegFormer (B4)","metrics":{"mIOU":"54.8"},"uses_additional_data":false,"paper_date":"2021-05-31","paper":"/paper/segformer-simple-and-efficient-design-for","paper_url":"https://arxiv.org/abs/2105.15203v3","paper_title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","code":"https://github.com/huggingface/transformers","n_code_links":28,"syntology":{"n_ran":64,"n_unverified":22,"n_samples":86,"n_pointer_only_licence":15}},{"rank_in_archive_order":37,"model":"SpiderMesh (ResNet-50)","metrics":{"mIOU":"54.4"},"uses_additional_data":false,"paper_date":"2023-03-15","paper":"/paper/spidermesh-spatial-aware-demand-guided","paper_url":"https://arxiv.org/abs/2303.08692v2","paper_title":"SpiderMesh: Spatial-aware Demand-guided Recursive Meshing for RGB-T Semantic Segmentation","code":"https://github.com/leofansq/spidermesh","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":38,"model":"SegFormer (B2)","metrics":{"mIOU":"53.2"},"uses_additional_data":false,"paper_date":"2021-05-31","paper":"/paper/segformer-simple-and-efficient-design-for","paper_url":"https://arxiv.org/abs/2105.15203v3","paper_title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","code":"https://github.com/huggingface/transformers","n_code_links":28,"syntology":{"n_ran":64,"n_unverified":22,"n_samples":86,"n_pointer_only_licence":15}},{"rank_in_archive_order":39,"model":"RTFNet","metrics":{"mIOU":"53.2"},"uses_additional_data":false,"paper_date":"2019-03-13","paper":"/paper/rtfnet-rgb-thermal-fusion-network-for","paper_url":"https://ieeexplore.ieee.org/abstract/document/8666745","paper_title":"RTFNet: RGB-Thermal Fusion Network for Semantic Segmentation of Urban Scenes","code":"https://github.com/yuxiangsun/RTFNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":40,"model":"HRNet","metrics":{"mIOU":"51.7"},"uses_additional_data":false,"paper_date":"2019-08-20","paper":"/paper/190807919","paper_url":"https://arxiv.org/abs/1908.07919v2","paper_title":"Deep High-Resolution Representation Learning for Visual Recognition","code":"https://github.com/open-mmlab/mmdetection","n_code_links":42,"syntology":{"n_ran":14,"n_unverified":20,"n_samples":34,"n_pointer_only_licence":16}},{"rank_in_archive_order":41,"model":"APCNet","metrics":{"mIOU":"49.0"},"uses_additional_data":false,"paper_date":"2019-06-01","paper":"/paper/adaptive-pyramid-context-network-for-semantic","paper_url":"http://openaccess.thecvf.com/content_CVPR_2019/html/He_Adaptive_Pyramid_Context_Network_for_Semantic_Segmentation_CVPR_2019_paper.html","paper_title":"Adaptive Pyramid Context Network for Semantic Segmentation","code":"https://github.com/Dylan-get/APCNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":42,"model":"SwinT","metrics":{"mIOU":"49.0"},"uses_additional_data":false,"paper_date":"2021-03-25","paper":"/paper/swin-transformer-hierarchical-vision","paper_url":"https://arxiv.org/abs/2103.14030v2","paper_title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","code":"https://github.com/huggingface/transformers","n_code_links":80,"syntology":{"n_ran":120,"n_unverified":87,"n_samples":207,"n_pointer_only_licence":43}},{"rank_in_archive_order":43,"model":"PST900","metrics":{"mIOU":"48.4"},"uses_additional_data":false,"paper_date":"2019-09-20","paper":"/paper/pst900-rgb-thermal-calibration-dataset-and","paper_url":"https://arxiv.org/abs/1909.10980v1","paper_title":"PST900: RGB-Thermal Calibration, Dataset and Segmentation Network","code":"https://github.com/ShreyasSkandanS/pst900_thermal_rgb","n_code_links":1,"syntology":null},{"rank_in_archive_order":44,"model":"FTNet","metrics":{"mIOU":"47.12"},"uses_additional_data":false,"paper_date":"2021-10-26","paper":"/paper/ftnet-feature-transverse-network-for-thermal","paper_url":"https://ieeexplore.ieee.org/abstract/document/9585453","paper_title":"FTNet: Feature Transverse Network for Thermal Image Semantic Segmentation","code":"https://github.com/shreyaskamathkm/FTNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":45,"model":"ACNet","metrics":{"mIOU":"46.3"},"uses_additional_data":false,"paper_date":"2019-05-24","paper":"/paper/acnet-attention-based-network-to-exploit","paper_url":"https://arxiv.org/abs/1905.10089v1","paper_title":"ACNet: Attention Based Network to Exploit Complementary Features for RGBD Semantic Segmentation","code":"https://github.com/anheidelonghu/ACNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":46,"model":"Depth-aware CNN","metrics":{"mIOU":"46.1"},"uses_additional_data":false,"paper_date":"2018-03-19","paper":"/paper/depth-aware-cnn-for-rgb-d-segmentation","paper_url":"http://arxiv.org/abs/1803.06791v1","paper_title":"Depth-aware CNN for RGB-D Segmentation","code":"https://github.com/laughtervv/DepthAwareCNN","n_code_links":4,"syntology":{"n_ran":1,"n_unverified":10,"n_samples":11,"n_pointer_only_licence":0}},{"rank_in_archive_order":47,"model":"PSPNet","metrics":{"mIOU":"46.1"},"uses_additional_data":false,"paper_date":"2016-12-04","paper":"/paper/pyramid-scene-parsing-network","paper_url":"http://arxiv.org/abs/1612.01105v2","paper_title":"Pyramid Scene Parsing Network","code":"https://github.com/tensorflow/models","n_code_links":67,"syntology":{"n_ran":7,"n_unverified":22,"n_samples":29,"n_pointer_only_licence":5}},{"rank_in_archive_order":48,"model":"SA-Gate","metrics":{"mIOU":"45.8"},"uses_additional_data":false,"paper_date":"2020-07-17","paper":"/paper/bi-directional-cross-modality-feature","paper_url":"https://arxiv.org/abs/2007.09183v1","paper_title":"Bi-directional Cross-Modality Feature Propagation with Separation-and-Aggregation Gate for RGB-D Semantic Segmentation","code":"https://github.com/charlesCXK/RGBD_Semantic_Segmentation_PyTorch","n_code_links":2,"syntology":null},{"rank_in_archive_order":49,"model":"UNet","metrics":{"mIOU":"45.1"},"uses_additional_data":false,"paper_date":"2015-05-18","paper":"/paper/u-net-convolutional-networks-for-biomedical","paper_url":"http://arxiv.org/abs/1505.04597v1","paper_title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","code":"https://github.com/labmlai/annotated_deep_learning_paper_implementations","n_code_links":487,"syntology":{"n_ran":518,"n_unverified":239,"n_samples":757,"n_pointer_only_licence":426}},{"rank_in_archive_order":50,"model":"FRRN","metrics":{"mIOU":"44.2"},"uses_additional_data":false,"paper_date":"2016-11-24","paper":"/paper/full-resolution-residual-networks-for","paper_url":"http://arxiv.org/abs/1611.08323v2","paper_title":"Full-Resolution Residual Networks for Semantic Segmentation in Street Scenes","code":"https://github.com/TobyPDE/FRRN","n_code_links":4,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":51,"model":"CCNet","metrics":{"mIOU":"43.3"},"uses_additional_data":false,"paper_date":"2018-11-28","paper":"/paper/ccnet-criss-cross-attention-for-semantic","paper_url":"https://arxiv.org/abs/1811.11721v2","paper_title":"CCNet: Criss-Cross Attention for Semantic Segmentation","code":"https://github.com/open-mmlab/mmsegmentation","n_code_links":4,"syntology":{"n_ran":10,"n_unverified":4,"n_samples":14,"n_pointer_only_licence":0}},{"rank_in_archive_order":52,"model":"SegNet","metrics":{"mIOU":"42.3"},"uses_additional_data":false,"paper_date":"2015-11-02","paper":"/paper/segnet-a-deep-convolutional-encoder-decoder","paper_url":"http://arxiv.org/abs/1511.00561v3","paper_title":"SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation","code":"https://github.com/PaddlePaddle/PaddleSeg","n_code_links":74,"syntology":{"n_ran":9,"n_unverified":35,"n_samples":44,"n_pointer_only_licence":10}},{"rank_in_archive_order":53,"model":"DANet","metrics":{"mIOU":"41.3"},"uses_additional_data":false,"paper_date":"2018-09-09","paper":"/paper/dual-attention-network-for-scene-segmentation","paper_url":"http://arxiv.org/abs/1809.02983v4","paper_title":"Dual Attention Network for Scene Segmentation","code":"https://github.com/xmu-xiaoma666/External-Attention-pytorch","n_code_links":12,"syntology":{"n_ran":0,"n_unverified":7,"n_samples":7,"n_pointer_only_licence":5}},{"rank_in_archive_order":54,"model":"MFNet","metrics":{"mIOU":"39.7"},"uses_additional_data":false,"paper_date":"2017-12-14","paper":"/paper/mfnet-towards-real-time-semantic-segmentation","paper_url":"https://ieeexplore.ieee.org/abstract/document/8206396","paper_title":"MFNet: Towards real-time semantic segmentation for autonomous vehicles with multi-spectral scenes","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":55,"model":"ERFNet","metrics":{"mIOU":"36.1"},"uses_additional_data":false,"paper_date":"2017-10-09","paper":"/paper/erfnet-efficient-residual-factorized-convnet","paper_url":"https://ieeexplore.ieee.org/abstract/document/8063438","paper_title":"ERFNet: Efficient Residual Factorized ConvNet for Real-time Semantic Segmentation","code":"https://github.com/osmr/imgclsmob","n_code_links":13,"syntology":null}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 7,081 of the 9,623 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9623,"papers_checked":7081,"papers_extracted_not_yet_verified":217,"boards_without_verdict":27,"papers_not_yet_extracted":2325},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-25T09:33:49+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":23,"rows_with_any_sample_ran":21,"distinct_papers_with_graph_line":18,"distinct_papers_with_any_sample_ran":16,"samples_over_distinct_papers":{"n_ran":804,"n_unverified":465,"n_samples":1269,"n_pointer_only_licence":548,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":873,"n_unverified":487,"n_samples":1360,"n_pointer_only_licence":566,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}